© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14261
    Prev
    Next
    INDEX
    Explanations

    HTML or configuration code with labels and values

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.94
     Monfieur
    -0.76
     Efq
    -0.75
    ChildScrollView
    -0.69
     poveznice
    -0.68
     reaſon
    -0.66
     Anſ
    -0.66
     iſt
    -0.66
    ſelves
    -0.65
     препратки
    -0.65
    POSITIVE LOGITS
    ValueGeneration
    0.46
     transfieras
    0.44
     sposob
    0.44
    онер
    0.44
     Discovery
    0.43
    LookAnd
    0.42
     (!_
    0.41
     me
    0.41
    ########.
    0.41
    }}],
    0.41
    Activations Density 0.435%

    No Known Activations